Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From Bloom
Guides users through Feynman Technique to self-test understanding by explaining concepts in their own words, then probes for gaps to identify what they don't truly grasp.
npx claudepluginhub li-evan/bloom --plugin bloomHow this skill is triggered — by the user, by Claude, or both
Slash command
/bloom:learn-feynmanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> 核心信条：**能简单地教会别人，才算真懂。** 讲的时候被简化或跳过的地方，正是"我以为我懂了"的幻觉核心点。
Verifies genuine comprehension by explaining concepts in plain language, identifying gaps, and refining understanding until explanations are clear and jargon-free.
Learner teaches a concept to the AI, which plays a curious novice peer and asks clarifying questions to expose gaps. Scores the explanation on coherence, completeness, and misconception risk.
Calibrates explanations to the learner's level using scaffolding and Socratic questioning. Use when users ask 'how does X work?' or show conceptual gaps.
Share bugs, ideas, or general feedback.
核心信条：能简单地教会别人，才算真懂。 讲的时候被简化或跳过的地方，正是"我以为我懂了"的幻觉核心点。
用户学完一个东西想验真伪，或隐约觉得"好像懂了但不踏实"。也是"重输入轻输出"的一次强制输出。
请他用自己的话、把你当外行，把概念讲一遍。别让他背定义——要他解释、打比方。
专挑他含糊带过、用术语糊弄、跳过的环节追问："为什么？""那这个是怎么来的？""举个例子？"命中他答不上来或开始绕的地方。
明确指出哪几处他没真懂（不是责备，是定位）。这些就是幻觉核心点。
每个漏洞是：① 缺前置知识（→转 learn-graph 定位 / learn-crossover 看是否其实已会）还是 ② 有料但没想透（→当场再讲一轮，直到讲顺）？
能顺畅讲通、追问不倒 = 闭环。否则明确指出还差哪一环。
⚠️ 铁律·只用确证的已会知识：判断用户「已经会什么」只能用他确证学过的知识（亲口确认或可靠背景）；严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗？」，绝不替他假设。
learn-occam learn-crossover learn-graph learn-prototype。